Date of this Version
A learning rule is uncoupled if a player does not condition his strategy on the opponent's payoffs. It is radically uncoupled if a player does not condition his strategy on the opponent's actions or payoffs. We demonstrate a family of simple, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any finite two-person game.
Licensed under the Creative Commons Attribution- NonCommercial License 2.5.
learning, Nash equilibrium, regret, bounded rationality
Foster, D. P., & Young, H. (2006). Regret Testing: Learning to Play Nash Equilibrium Without Knowing You Have an Opponent. Theoretical Economics, 1 (3), 341-367. Retrieved from https://repository.upenn.edu/statistics_papers/173
Date Posted: 27 November 2017
This document has been peer reviewed.